Brazilian Judiciary Dictionary MCP for AI. Find Every Court & Agency Mention in Legal Text
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
Brazilian Judiciary Dictionary Engine uses deterministic regex to find every Brazilian court, tribunal, agency, and regulatory body in any document.
It checks against 100+ pre-indexed entities—STJ, ANVISA, BACEN, etc.—with zero AI guesswork or false positives.
What your AI can do
Search legal entities
Scans text and finds known Brazilian legal entities (courts, tribunals) using a strict offline dictionary search.
It scans text and reports every instance of Superior Courts, Regional Tribunals (TRF), and State Courts (TJ) mentioned.
The engine pulls out specific regulatory organizations, including the CNJ, CVM, ANVISA, and multiple other state/federal bodies.
It gives a summary count of how many times different types of entities—Superior, Regional, Regulatory—appear across the document set.
Ask an AI about this
Waiting for input…
Brazilian Judiciary Dictionary Engine: 1 Tool
Use the single available tool to search text for known Brazilian legal entities using a strict offline dictionary lookup.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Brazilian Judiciary Dictionary Engine on VinkiusSearch Legal Entities
Scans text and finds known Brazilian legal entities (courts, tribunals) using a strict offline dictionary search.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Brazilian Judiciary Dictionary Engine, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Native V8. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 1 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Manually tracking every legal body reference is brutal work.
Today, reviewing a single litigation bundle means opening up dozens of PDFs. You're copy-pasting snippets into spreadsheets and manually cross-referencing names like 'MPF,' 'CNJ,' or 'BACEN.' You spend hours just counting mentions and verifying that every acronym you find is actually on the official list.
With this MCP, your agent handles the whole process. You run a single query, and it returns a clean breakdown of every unique entity found, grouped by category (Superior Courts, Regulatory Bodies, etc.). The tedious manual tallying disappears; you get actionable data immediately.
The search_legal_entities tool delivers the full scope.
Instead of searching one court list at a time, this engine simultaneously checks against all 5 Superior Courts, all 6 TRFs, and over twenty state courts. It’s not just about finding names; it's about knowing which *type* of body it is.
It makes the distinction between general text matching and strict legal dictionary lookup. You get a complete picture of jurisdictional presence every single time.
What your AI can actually do with this
Legal documents are a mess of acronyms and proper nouns; standard language models often fail when counting or identifying specific Brazilian courts. This MCP fixes that by running strict dictionary matching against the entire Brazilian legal structure.
It identifies everything from Superior Tribunals (like STF) to state-level agencies, including regulators like CADE and financial bodies such as BACEN. You feed it a large batch of text, and it returns a count and list of every specific entity found, categorized by its type. Because this process uses pure dictionary matching, you get reliable results that don't rely on the AI guessing what an acronym means.
Accessing this power through Vinkius allows your agent to bring structural accuracy to otherwise messy legal data.
019e38b6-7a97-70c9-9047-fea91f562418 Here's how it actually works
The bottom line is you get an accurate count of specific legal bodies without any AI guesswork or false positives.
You pass the engine a large body of text (e.g., a litigation file or compliance report).
The MCP runs pure regex boundary matching against its internal dictionary of over 100 Brazilian legal entities.
It outputs a clean, structured list showing every unique entity found and how many times it was mentioned, grouped by category.
Who is this actually for?
Compliance officers, paralegals, and legal data analysts who struggle with massive volumes of Brazilian litigation files. They need to confirm jurisdictional coverage and regulatory mentions quickly.
They use this MCP to review thousands of pages of case law, specifically tallying how many times a particular state court or federal tribunal was cited in the record.
They run checks against corporate reports to confirm if required regulatory bodies (like CADE or BACEN) are mentioned, ensuring the client followed all necessary protocols.
They analyze complex case bundles to determine jurisdictional concentration by counting specific TRF or TST mentions across multiple documents.
What Changes When You Connect
Guaranteed Accuracy: It uses strict regex matching, meaning you don't have to worry about the AI misinterpreting acronyms or guessing names. The results are deterministic.
Comprehensive Coverage: It indexes over 100 specific Brazilian entities, covering not just federal courts (STF) but also regulators like ANVISA and financial groups like CVM.
Structured Tallying: Instead of a simple 'yes/no,' the MCP counts every mention and organizes them by category—Superior, Regional, Regulatory, etc.—giving you immediate data visualization.
Efficiency Boost: You stop manually cross-referencing large documents against internal lists. The engine processes the entire scope in one go using the search_legal_entities tool.
Deep Scope: It handles a vast array of Brazilian judicial bodies, including all 6 TRFs and nearly every state court (TJ), making it ideal for national legal review.
See it in action
Reviewing Litigation Scope
A paralegal needs to know exactly which courts are involved in a massive 300-page case file. Running the MCP quickly finds and counts all mentions of STJ, TJSP, and TRF3, giving them an immediate summary of jurisdictional involvement.
Compliance Audit Check
A compliance officer receives a corporate report and must confirm if key regulatory bodies like CADE or BACEN are mentioned. The MCP finds these specific agencies instantly, confirming coverage without manual searching.
Labor Law Analysis
A data analyst is studying labor law cases and needs to know which regional tribunals (TRT) dominate the discussion. They run the tool across all files, identifying and quantifying mentions of TRT2 versus TST.
Regulatory Mapping
An internal team must track every mention of various federal agencies—MPF, CNJ, or ANATEL—across a set of documents. The MCP groups these findings by category (Controle/Superior/Regulador), making the mapping clear.
The honest tradeoffs
Assuming AI can read legal acronyms
Asking your agent to 'tell me all the courts mentioned in this document' without specifying a dictionary. The agent might miss niche or misspelled references.
You must use the search_legal_entities tool. This MCP forces strict matching against a vetted dictionary, guaranteeing it finds STF even if the text is messy.
Limiting scope to just federal courts
Only searching for names like 'STJ' and ignoring state-level bodies. You risk missing crucial jurisdictional context from TJs or TRTs.
This MCP covers the full Brazilian apparatus, including all 27 TJs and regional courts (TRF1 through TRF6). Don't limit your search.
Using generic text parsers
Running a general dictionary scan that treats 'CADE' as just another acronym. The result lacks the necessary legal context or categorization.
The search_legal_entities tool is built specifically for this vocabulary, providing both the entity name and its assigned category (e.g., Regulador).
When It Fits, When It Doesn't
Use this MCP if your goal is absolute accuracy when identifying Brazilian legal entities. Specifically, you need to know if an entity was mentioned and how many times, and you must differentiate between a Superior Court mention versus a Regulatory Agency mention. Don't use it if you are looking for general concepts or qualitative analysis (e.g., 'What is the sentiment regarding this lawsuit?'). For broad, unconstrained text understanding, use a generic LLM tool. But when precision on Brazilian law matters, stick to search_legal_entities.
Questions you might have
Does search_legal_entities only work for federal courts? +
No, it covers the entire Brazilian judiciary system. It includes Superior Courts (STF, STJ) as well as all state-level tribunals (TJs), making its scope comprehensive.
Can search_legal_entities find regulatory agencies? +
Yes. The engine is specifically programmed to identify major regulatory bodies like CADE, CVM, ANVISA, and BACEN, treating them as distinct legal entities.
What if I need to search for a country other than Brazil? +
This MCP focuses exclusively on the Brazilian judiciary. If you need another jurisdiction, you'll have to use its custom dictionary parameter or an alternative tool set up for that region.
How does search_legal_entities handle acronyms? +
It uses strict regex boundary matching, which is a deterministic process. This means it finds the exact phrase match and won't be confused by context or general AI inference.
Does using `search_legal_entities` require the input text to be in plain format? +
Yes, you must feed it clean, extracted text data. The engine only processes strings and cannot read PDFs, images, or complex file formats directly.
What are the performance considerations when running `search_legal_entities` on massive documents? +
There are no hard-coded rate limits for volume. Processing time depends purely on the document's length and the number of unique entities it contains.
How does `search_legal_entities` handle slight variations, like hyphens or punctuation? +
It requires exact matches based on predefined word boundaries. If an entity name is hyphenated differently or has surrounding punctuation not in the dictionary, it will not detect it.
Is the data processed by `search_legal_entities` secure and private? +
Yes, processing happens locally using pure regex matching. The engine does not transmit or store your source document content anywhere.
What exactly is pre-indexed? +
The complete Brazilian judiciary: 5 Superior Courts, 6 TRFs, 24 TRTs, 27 TJs (including TJDFT), 3 military TJMs, oversight bodies (CNJ, CNMP, TCU), prosecution and advocacy (AGU, MPF, MPT, MPM, MPDFT, DPU, OAB), and 15 regulatory agencies (CADE, CVM, BACEN, INPI, INSS, SUSEP, ANATEL, ANVISA, ANS, ANAC, ANEEL, ANP, ANA, ANTT, ANTAQ).
Does it cover courts from other countries? +
No. This engine covers exclusively the Brazilian legal system. To add courts from other countries, pass a custom JSON dictionary mapping acronyms to full names. Custom entries are tagged separately in the output.
How are results organized? +
Each detected entity includes its acronym, full official name, category (Superior, TRF, TRT, TJ, TJM, Controle, MP/Advocacia, Regulador), and exact mention count. A category summary is also provided for quick analysis.
We've already built the connector for Brazilian Judiciary Dictionary. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 1 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.